Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support repetition of \d and \D in regexp functions #4469

Merged
merged 1 commit into from
Jan 7, 2022
Merged

Support repetition of \d and \D in regexp functions #4469

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions sql-plugin/src/main/scala/com/nvidia/spark/rapids/RegexParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2021, NVIDIA CORPORATION.
* Copyright (c) 2021-2022, NVIDIA CORPORATION.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
Expand Down Expand Up @@ -571,10 +571,11 @@ class CudfRegexTranspiler(replace: Boolean) {
// example: pattern " ?", input "] b[", replace with "X":
// java: X]XXbX[X
// cuDF: XXXX] b[
// see https://github.com/NVIDIA/spark-rapids/issues/4468
throw new RegexUnsupportedException(
"regexp_replace on GPU does not support repetition with ? or *")

case (RegexEscaped(_), _) =>
case (RegexEscaped(ch), _) if ch != 'd' && ch != 'D' =>
// example: "\B?"
throw new RegexUnsupportedException(nothingToRepeat)

Expand Down
17 changes: 16 additions & 1 deletion tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2021, NVIDIA CORPORATION.
* Copyright (c) 2021-2022, NVIDIA CORPORATION.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
Expand Down Expand Up @@ -232,6 +232,21 @@ class RegularExpressionTranspilerSuite extends FunSuite with Arm {
assertCpuGpuMatchesRegexpFind(patterns, inputs)
}

test("compare CPU and GPU: find digits") {
val patterns = Seq("\\d", "\\d+", "\\d*", "\\d?",
"\\D", "\\D+", "\\D*", "\\D?")
val inputs = Seq("a", "1", "12", "a12z", "1az2")
assertCpuGpuMatchesRegexpFind(patterns, inputs)
}

test("compare CPU and GPU: replace digits") {
// note that we do not test with quantifiers `?` or `*` due
// to https://github.com/NVIDIA/spark-rapids/issues/4468
val patterns = Seq("\\d", "\\d+", "\\D", "\\D+")
val inputs = Seq("a", "1", "12", "a12z", "1az2")
assertCpuGpuMatchesRegexpReplace(patterns, inputs)
}

private val REGEXP_LIMITED_CHARS = "|()[]{},.^$*+?abc123x\\ \tBsdwSDW"

test("compare CPU and GPU: regexp find fuzz test with limited chars") {
Expand Down